Petabit to Exbibit

One petabit = 10¹⁵ bits = 125 terabytes. To put it in perspective: the entire text content of all English Wikipedia articles is roughly 4 GB — so a petabit could hold about 31,000 copies of it. A petabit per second link could transfer all of Wikipedia's text content in about 32 microseconds.

As of 2024, no single commercial link carries 1 Pbps, but laboratory experiments have demonstrated fiber optic transmission exceeding 1 Pbps using dense wavelength-division multiplexing on a single fiber strand. Commercial submarine cables aggregate hundreds of terabits per second across many fibers and wavelengths, collectively reaching petabit-scale capacity per cable system.

A petabit (Pb) = 10¹⁵ bits. A petabyte (PB) = 10¹⁵ bytes = 8 petabits. Storage systems (data centers, archival systems) use petabytes for capacity; aggregate network throughput uses petabits per second. An exabyte-scale data center stores 1,000 petabytes; its internal network may carry multiple petabits per second of traffic.

Qubits and classical bits solve fundamentally different problems — qubits will not simply replace petabit-scale classical storage or networking. A quantum computer with 1,000 logical qubits can explore 2¹⁰⁰⁰ states simultaneously, but measuring those qubits collapses them to classical bits. Quantum networks will likely handle key distribution and entanglement sharing at kilobit-to-megabit rates, while classical infrastructure continues to move petabits of bulk data. The two technologies are complementary, not substitutional.

Submarine fiber optic cables are built by a handful of companies (SubCom, NEC, Alcatel Submarine Networks) and typically cost $200–500 million per system. A modern cable contains 12–24 fiber pairs, each carrying hundreds of wavelengths via dense wavelength-division multiplexing, reaching 400+ Tbps aggregate capacity per cable. Cables are designed to last 25 years on the ocean floor. When faults occur, specialised cable repair ships (fewer than 60 exist worldwide) locate breaks using optical time-domain reflectometry and splice repairs at sea — a process that can take days to weeks depending on depth and weather.

An exabit (Ebit) = 10¹⁸ bits (SI decimal). An exbibit (Eibit) = 2⁶⁰ bits ≈ 1.1529 × 10¹⁸ bits (IEC binary). Exbibit is 15.29% larger — the cumulative product of using 1,024 instead of 1,000 at each of six prefix steps. This is the largest practically relevant SI vs IEC gap for bit units in current storage contexts.

Exbibit is used in: computer science academic literature on exascale computing, theoretical storage system design papers, and formal IEC/IEEE standards. No commercial product, OS, or consumer application currently displays exbibits. It is primarily a unit for academic and standards consistency — ensuring the IEC prefix family extends uniformly from kibi- to exbi- (and beyond to zebi- and yobi-).

After exbibit (Eibit, 2⁶⁰ bits) come: zebibit (Zibit, 2⁷⁰ bits) and yobibit (Yibit, 2⁸⁰ bits). These are defined in the IEC 80000-13 standard but have no current practical applications. The IEC binary prefix family deliberately mirrors the SI prefix family, ensuring consistent naming as computing scale continues to grow.

Frontier (Oak Ridge, 2022) achieved 1.194 exaFLOPS, with its Slingshot-11 fabric moving data at aggregate rates measurable in exbibits per second across 9,408 nodes. Aurora (Argonne, 2024) targets similar throughput with over 63,000 GPUs. At these scales, a single checkpoint of a full-system simulation can exceed 1 Eibit of state data, making exbibit a natural unit for describing I/O bandwidth requirements.

The IEC currently defines up to yobibit (Yibit, 2⁸⁰ bits). In 2022, the SI system added ronna- (10²⁷) and quetta- (10³⁰), but the IEC has not yet created matching binary prefixes (ronnibit? quettibit?). With global data creation projected to exceed 1 yottabit annually by the 2030s, pressure is mounting for the IEC to extend the binary prefix family — though the naming convention ("ronnibi-"?) remains an open question.